恢复保存的TensorFlow模型以对测试集进行评估 [英] Restoring saved TensorFlow model to evaluate on test set

问题描述

我已经看到一些帖子关于恢复 TF $ c>模型和上的 Google 文档页面导出图形，但我认为我缺少了一些东西。

I have seen a few posts on restoring TF models and the Google doc page on exporting graphs but I think I am missing something.

我在 Gist 将模型和此utils文件一起保存到定义模型

I use the code in this Gist to save the model along with this utils file to which defines the model

现在，我想还原它并在以前看不见的测试数据中运行，如下所示：

Now I would like to restore it and run in a previously unseen test data as follows:

def evaluate(X_data, y_data):
    num_examples = len(X_data)
    total_accuracy = 0
    total_loss = 0
    sess = tf.get_default_session()
    acc_steps = len(X_data) // BATCH_SIZE
    for i in range(acc_steps):
        batch_x, batch_y = next_batch(X_val, Y_val, BATCH_SIZE)

        loss, accuracy = sess.run([loss_value, acc], feed_dict={
                images_placeholder: batch_x,
                labels_placeholder: batch_y,
                keep_prob: 0.5
                })
        total_accuracy += (accuracy * len(batch_x))
        total_loss += (loss * len(batch_x))
    return (total_accuracy / num_examples, total_loss / num_examples)

## re-execute the code that defines the model

# Image Tensor
images_placeholder = tf.placeholder(tf.float32, shape=[None, 32, 32, 3], name='x')

gray = tf.image.rgb_to_grayscale(images_placeholder, name='gray')

gray /= 255.

# Label Tensor
labels_placeholder = tf.placeholder(tf.float32, shape=(None, 43), name='y')

# dropout Tensor
keep_prob = tf.placeholder(tf.float32, name='drop')

# construct model
logits = inference(gray, keep_prob)

# calculate loss
loss_value = loss(logits, labels_placeholder)

# training
train_op = training(loss_value, 0.001)

# accuracy
acc = accuracy(logits, labels_placeholder)

with tf.Session() as sess:
    loader = tf.train.import_meta_graph('gtsd.meta')
    loader.restore(sess, tf.train.latest_checkpoint('./'))
    sess.run(tf.initialize_all_variables())   
    test_accuracy = evaluate(X_test, y_test)
    print("Test Accuracy = {:.3f}".format(test_accuracy[0]))

我得到的测试准确度仅为 3％。但是，如果我在训练模型后不关闭笔记本电脑并立即运行测试代码，则可以达到 95％的精度。

I'm getting a test accuracy of only 3%. However If I don't close the Notebook and run the test code immediately after training the model, I get a 95% accuracy.

这使我相信我没有正确加载模型？

This leads me to believe I'm not loading the model correctly?

推荐答案

问题来自这两行：

loader.restore(sess, tf.train.latest_checkpoint('./'))
sess.run(tf.initialize_all_variables())   

第一行从检查点加载保存的模型。第二行重新初始化模型中的所有变量（例如权重矩阵，卷积滤波器和偏差矢量），通常是随机数，然后覆盖

The first line loads the saved model from a checkpoint. The second line re-initializes all of the variables in the model (such as the weight matrices, convolutional filters, and bias vectors), usually to random numbers, and overwrites the loaded values.

解决方案很简单：删除第二行（ sess.run（tf.initialize_all_variables（））），然后将从检查点加载的训练值进行评估。

The solution is simple: delete the second line (sess.run(tf.initialize_all_variables())) and evaluation will proceed with the trained values loaded from the checkpoint.

PS。此更改极有可能给您带来有关未初始化的变量的错误。在这种情况下，您应该执行 sess.run（tf.initialize_all_variables（））来初始化未保存在检查点之前的变量，然后执行 loader.restore（sess，tf.train.latest_checkpoint（'./'))。

PS. There is a small chance that this change will give you an error about "uninitialized variables". In that case, you should execute sess.run(tf.initialize_all_variables()) to initialize any variables not saved in the checkpoint before executing loader.restore(sess, tf.train.latest_checkpoint('./')).

这篇关于恢复保存的TensorFlow模型以对测试集进行评估的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！